casarf commited on
Commit
ea63182
·
1 Parent(s): a33e3c4

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +5 -14
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2329
18
- - Validation Loss: 0.5445
19
- - Train Accuracy: 0.7349
20
- - Epoch: 9
21
 
22
  ## Model description
23
 
@@ -43,16 +43,7 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
- | 0.6244 | 0.5609 | 0.7108 | 0 |
47
- | 0.5031 | 0.5148 | 0.7711 | 1 |
48
- | 0.3733 | 0.5206 | 0.7590 | 2 |
49
- | 0.2865 | 0.5363 | 0.7349 | 3 |
50
- | 0.2335 | 0.5445 | 0.7349 | 4 |
51
- | 0.2305 | 0.5445 | 0.7349 | 5 |
52
- | 0.2291 | 0.5445 | 0.7349 | 6 |
53
- | 0.2302 | 0.5445 | 0.7349 | 7 |
54
- | 0.2323 | 0.5445 | 0.7349 | 8 |
55
- | 0.2329 | 0.5445 | 0.7349 | 9 |
56
 
57
 
58
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.6564
18
+ - Validation Loss: 0.5867
19
+ - Train Accuracy: 0.6988
20
+ - Epoch: 0
21
 
22
  ## Model description
23
 
 
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 0.6564 | 0.5867 | 0.6988 | 0 |
 
 
 
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c056bdad14927bb740e046dfb49edfa062d50aa8bf621cd3a864fde842eacd16
3
  size 267951808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e9610faa70c71b44b1f5afc72ecc5c247b87077628345a89f998332404eaf3
3
  size 267951808